mlsanityData to 14 Oct 2026

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

arXiv 2507.20280 ↗First posted 27 Jul 2025cs.AI cs.CLcited by 43

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools demands substantial domain expertise. While Large Language Models (LLMs) show promise in tool automation, they struggle to seamlessly integrate and orchestrate multiple tools for complex scientific workflows. Here, we present SciToolAgent, an LLM-powered agent that automates hundreds of scientific tools across biology, chemistry, and materials science. At its core, SciToolAgent leverages a scientific tool knowledge graph that enables intelligent tool selection and execution through graph-based retrieval-augmented generation. The agent also incorporates a comprehensive safety-checking module to ensure responsible and ethical tool usage. Extensive evaluations on a curated benchmark demonstrate that SciToolAgent significantly outperforms existing approaches. Case studies in protein engineering, chemical reactivity prediction, chemical synthesis, and metal-organic framework screening further demonstrate SciToolAgent's capability to automate complex scientific workflows, making advanced research tools accessible to both experts and non-experts.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 23 of its 46 references that are in the map. First posted on arXiv 27 Jul 2025.

Builds on

23 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Controlling risks of AI in chemical science with agents11 Dec

Other references · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2023A Survey of Large Language Modelscited by 2,576
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  8. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  9. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248
  10. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 240
  11. 2018Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Predictioncited by 229
  12. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 185
10 more
  1. 2023ChatEDA: A Large Language Model Powered Autonomous Agent for EDAcited by 122
  2. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 117
  3. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  4. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 64
  5. 2023MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledgecited by 63
  6. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  7. 2024BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuningcited by 54
  8. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Modelscited by 42
  9. 2024CACTUS: Chemistry Agent Connecting Tool-Usage to Sciencecited by 33
  10. 2023Language models in molecular discoverycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 14; 2026: 29.

43 papers.

Sort:

By area:

  1. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  2. 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolutioncited by 34
  3. 2025Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAMcited by 15
  4. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  5. 2025HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Researchcited by 11
  6. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  7. 2025Code2MCP: Transforming Code Repositories into MCP Servicescited by 10
  8. 2026AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentationcited by 9
  9. 2026El Agente Quntur: A research collaborator agent for quantum chemistrycited by 8
  10. 2025Dynamic Tool Dependency Retrieval for Lightweight Function Callingcited by 7
  11. 2025K-Dense Analyst: Towards Fully Automated Scientific Analysiscited by 6
  12. 2025Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memorycited by 6
31 more
  1. 2026Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesiscited by 6
  2. 2026SimMOF: AI agent for Automated MOF Simulationscited by 5
  3. 2026Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observerscited by 4
  4. 2026MDGYM: Benchmarking AI Agents on Molecular Simulationscited by 4
  5. 2025ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challengescited by 3
  6. 2026Learning Agent Routing From Early Experiencecited by 3
  7. 2025AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.orgcited by 2
  8. 2026Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Predictioncited by 2
  9. 2026CeProAgents: A Hierarchical Agents System for Automated Chemical Process Developmentcited by 2
  10. 2026ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agentscited by 2
  11. 2025CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automationcited by 1
  12. 2026Embodied Science: Closing the Discovery Loop with Agentic Embodied AIcited by 1
  13. 2026Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflowscited by 1
  14. 2026Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agentscited by 1
  15. 2026Pepti-Agent: An AI Agent for Peptide Design and Optimizationcited by 1
  16. 2025Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactionscited by 0
  17. 2026Autonomous computational catalysis through an agentic research systemcited by 0
  18. 2026InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computingcited by 0
  19. 2026The limits of bio-molecular modeling with large language models : a cross-scale evaluationcited by 0
  20. 2026A collaborative agent with two lightweight synergistic models for autonomous crystal materials researchcited by 0
  21. 2026Starter-Iterator Neural Operator: A Unified Architecture for High-Fidelity Forward and Inverse PDE Problemscited by 0
  22. 2026Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agentscited by 0
  23. 2026MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Modelscited by 0
  24. 2026SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisitioncited by 0
  25. 2026SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discoverycited by 0
  26. 2026Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scalecited by 0
  27. 2026Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignmentcited by 0
  28. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0
  29. 2026Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Designcited by 0
  30. 2026Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoningcited by 0
  31. 2026Triage-PiEvo: Evidence Admission for Principle-Evolving Scientific Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
  2. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
  3. 2026Agents-K1: Towards Agent-native Knowledge Orchestration
  4. 2026From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry
  5. 2025Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
  6. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
  7. 2026M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
  8. 2026AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models